#AI #ChatGPT #Grok: Once artificial intelligence really gets going, how fast can the economy grow?

I followed the lead set by Tim Harford in "If AI lifts off, will living standards follow?" and asked ChatGPT and Grok.

I asked ChatGPT:

"Please, feel free to speculate… though in less than 300 words:

Once artificial intelligence really gets going, how fast can the economy grow? Five per cent a year? Ten per cent? Fifty per cent?"

ChatGPT answered:

"Speculating freely: once artificial intelligence truly integrates across the economy, the growth rate could, in principle, exceed anything we’ve seen in modern history. Traditional constraints—labor supply, managerial capacity, coordination costs—are precisely what AI promises to relax.

At the moderate end, AI might sustain global growth in the 5–7% range for decades, roughly doubling the pace of advanced economies today. That would already be transformative: compound growth at 7% doubles output every 10 years.

A more extreme possibility is 10–20% growth annually, if AI automates not just routine work but also much of scientific discovery, engineering, and entrepreneurship itself. In that case, the bottleneck of “who invents the next breakthrough” loosens, and innovation becomes continuous and self-reinforcing. Such growth rates imply doubling the economy every 3–7 years—levels usually associated with small frontier economies catching up, not the entire world.

The most radical speculation—50%+ annual growth—would mean AI essentially creates a self-improving system of production, design, and distribution, with humans struggling to keep up. That’s not just economic growth in the classical sense but something more akin to a civilizational transformation, where “GDP” may cease to measure what matters.

So the spectrum runs from a modest boost (5%) to explosive acceleration (>20%), depending on how fast AI can (1) replicate human-level reasoning, (2) integrate with physical production, and (3) avoid coordination and social frictions. In practice, political, regulatory, and resource constraints may prevent the highest numbers—but technically, nothing rules them out."

Would you like me to anchor this in historical parallels (e.g., Industrial Revolution, electricity, internet) to show what kind of multiplier might be realistic, versus purely speculative?

I said: Yes please, but in in less than 200 words.

ChatGPT said:

"Historically, big technologies lifted growth but within limits. The Industrial Revolution doubled Britain’s per-capita growth from ~0.3% to ~1% a year—huge by historical standards but gradual. The spread of electricity and mass production pushed U.S. growth to ~2–3% sustained. The computer and internet era gave a one-time boost, but growth rarely exceeded 4–5% in advanced economies.

AI differs because it can speed up not only production but also innovation itself. If it amplifies discovery like electricity amplified muscle power, we could see global growth at 5–7% for decades—unprecedented at scale. If AI can recursively accelerate research, growth could climb to 10–20%, closer to the explosive catch-up of “Asian Tigers,” but applied globally.

The leap to 50%+ annual growth has no historical parallel; it would be more like a technological singularity than a continuation of economic history. Past revolutions suggest sustained boosts are real, but explosive, runaway growth would mark a civilizational break rather than just “faster GDP.”

Do you want me to sketch what kind of constraints (energy, politics, social adjustment) might hold AI growth closer to the historical pattern than the singularity path?

I said: Yes please, but in in less than 200 words

ChatGPT said:

"Several constraints could keep AI-driven growth closer to historical patterns. Energy is a hard limit: exponential growth in computing and production demands vast power, and scaling renewable, nuclear, or other sources takes time. Physical capital—factories, housing, transport—cannot be replaced overnight, even if AI designs them instantly. Human adaptation is another brake: societies need time to retrain, absorb, and regulate, and resistance from workers, firms, or governments slows diffusion.

Coordination frictions also matter. Nations may restrict AI exports, regulate its use, or impose safety checks, curbing global acceleration. Meanwhile, resource bottlenecks—rare earths, chips, robotics hardware—could stall deployment. Finally, inequality and political backlash may block full adoption if many feel excluded or threatened.

These forces suggest AI could plausibly raise growth to 5–7%, maybe 10%, but sustained 20%+ requires solving energy, materials, and governance hurdles as quickly as technical ones. History shows revolutions spread in waves, not instant leaps."

Would you like me to quantify how fast GDP could double under each plausible growth rate (e.g., 5%, 10%, 20%) to make the comparison more tangible?

I said: For today this is enough. Thanks!

It said:You’re very welcome! I’ll be here if you want to continue the thread another day. Wishing you a good evening!

I asked Grok:

"Please, feel free to speculate… though in less than 300 words:

Once artificial intelligence really gets going, how fast can the economy grow? Five per cent a year? Ten per cent? Fifty per cent?"

Grok answered:

"Once AI truly accelerates—say, with AGI or superintelligence by the 2030s or 2040s—economic growth could shatter historical norms. Current global GDP growth hovers around 3%, but AI could amplify it dramatically through automation, innovation, and productivity surges.

In moderate scenarios, experts predict AI adding 1-2% annually to GDP via task automation and R&D boosts, pushing total growth to 4-5%. More optimistic views, like McKinsey's, foresee $4.4 trillion in annual value by 2030, potentially lifting growth to 5-10% as AI transforms industries. 

But if we hit a "technological singularity," where AI self-improves exponentially, growth could explode. Some models suggest superexponential rates, with GDP doubling yearly (100%+ growth) or faster, leading to 50% as a conservative floor in early phases. Imagine AI emulating human minds at scale, eradicating scarcity and enabling post-scarcity abundance. 

Risks abound—job displacement, inequality—but the upside? A hyper-accelerated economy, growing at rates we can't yet fathom, potentially 50% or beyond in a runaway AI boom. Speculatively, 10% seems plausible mid-term; 50%+ in full singularity mode."

I said: Thanks!

It answered: You're welcome! If you have more questions about AI or anything else, just ask.

Note: The answers are copied exactly from those given to me by ChatGPT and Grok

Here my many other questions to ChatGPT – Grok on bank regulations.

Human pilots and autopilots need to be trusting friends.

Sir, last year, flying to Washington DC, in a Boeing 337 MAX 9, the clouds were so low that the pilot missed the first approach to land at Dulles International Airport. We passengers were instructed: “Please, please completely turn off all, absolutely all your computers, iPad cellphones and similar, even if closed or placed in air-mode. We cannot afford any type of interference. The pilot has decided he can’t land the plane, and so he will have the auto-pilot do it.” 

Very long minutes of praying and checking up on co-passengers’ cellphones ensued. Finally, without having been able to see any land, thanks to God we landed.`` I asked my wife: “If they have to use the auto-pilot when things get really hard, why do they have pilots at all?”

Tim Harford answers that question in “Of top-notch algorithms and zoned-out humans” FT February 1. Harford writes: “A storm that blocked the sys­tem’s air­speed instru­ments with assist­ive fly-by-wire sys­tem that trans­lates the pilot’s jerky move­ments into smooth instructions. This makes it hard to crash an A330. But para­dox­ic­ally, it means that when a chal­lenge does occur, the pilots will have very little exper­i­ence to draw on as they try to meet that chal­lenge.”

What does it indicate as a solution? Clearly humans and autopilots need to communicate faster and clearer about who is more qualified to be in command. And that means they need to be able to trust each other much more.

Sir, after the experience I described, even though I have often complained about pain over my eyes when landing with a Boeing 337 MAX 9, probably because of some issues with its air pressure control, sincerely, after that landing, tell me how could I ever complain about that Boeing plane?

@PerKurowski

A strong national spirit/character is what’s most needed for any preparedness, even against a pandemic.

Sir, I refer to Tim Harford’s “Is it even pos­sible for coun­tries to pre­pare for a pan­demic?” FT June 24, 2023.

“Be pre­pared! It’s the scout’s motto. But pre­pared for what?” I was never a boy-scout but as I have understood that movement it was to be prepared courageously for the unexpected, not silently accepting a lockdown; and to be able to lit a fire without matches, not to learn to deploy sewage monitors.

So sadly, though Harford does indeed know much of economy, here I think he does not even scratch the surface of what’s most needed, like:

First: The understanding that, for a nation/society as a whole, a response to the pandemic can be much more harmful than the pandemic itself.

Second: That just as George Clemenceau opined, “War is too serious a matter to entrust to military men”, a pandemic is also too serious a matter to entrust to epidemiologists” Any preparedness against a pandemic must include a wide diversity of opinions.

Third: Information, information and information: With respect to this Harford mentions: “Joshua Gans, eco­nom­ist and author of The Pan­demic Inform­a­tion Solu­tion (2021), argues that we’ve learnt that pan­dem­ics can be thought of as inform­a­tion and incentive problems.” No, begin by giving the people full information and then let them understand and decide if and what incentives are needed.

In July 2020 I tweeted:

“Sweden kept all schools until 9thgrade open. Parents of children in 9th grade are almost always less than 50 years of age. In Sweden, as of July 24, out of 5,687 Coronavirus deaths 71, 1.2%, were younger than 50 years.”

“Conclusion: Keep schools open, keep older teachers at home and have grandparents refrain from hugging their grandchildren. Disseminating data on Covid-19 without discriminating by age, is in essence misinformation.”

Clearly information on the relation between Covid-19 and age was available but was not sufficiently provided. One explanation could be that the Covid-19 pandemic hit the world in the midst of a polarization pandemic. 17 October 2020 I wrote in a letter to FT “way too many polarization profiteers just don’t want harmony vaccines to appear.”

March 2020 I tweeted: 

“In February, I visited Churchill War Rooms in London Reading UK’s plans of building up herd immunity against coronavirus, I have a feeling Winston would have agreed with such stiff upper lip policy: “I have nothing to offer but fever, coughing, chills and shortness of breath”

Sir, Neville Chamberlain’s spirit inspired UK’s pandemic answer. Just like he is present in the risk weighted bank capital requirements which incentivize much more the refinancing of the “safer” present than the financing of the “riskier future”

I summarized the result of the above three failings in a letter published by the Washington Post in October 2020 in which I stated: "Roughly 90% of all coronavirus deaths will occur in those 60 years of age and older. Equally roughly 90% of the virus’s social and economic consequences will be paid by those younger than 60. It’s an intergenerational conflict of monstrous proportions."

PS. Sir, if you are interested you might want to read what ChatGPT – OpenAI answered when I asked "Suppose a virus hits a nation, and to its authorities its evident that its mortality rate depends the most on age. In such a case, transmitting data to the population about the total number of deaths without discriminating this by age, could that be deemed to be misinformation?"

https://perkurowski.blogspot.com/2023/06/ai-chatgpt-openai-if-mortality-rate-of.html

PS. Sir, you should be interested in the above, it evidences how humans can begin dialoguing with artificial intelligence, so as to have a better chance of keeping their Human Masters and appointed experts in check.

@PerKurowski

Basel Committee’s risk weighted bank capital requirements is fodder for our wishful thinking hopes.

I refer to Tim Harford’s “From forgeries to Covid-denial" On how we fool ourselves: Whether believing implausible statistics or falling for frauds, humans are addicted to wishful thinking” FT, January 30, 2021.

Sir, I ask, the Basel Committee’s risk weighted bank capital requirements, could that just be a forgery made to satisfy our deep wishes of our banks always being safe?

Now why so little objections? Edward Dolnick explained it with: “Experts have little choice but to put enormous faith in their own opinions. Inevitably, that opens the way to error, sometimes to spectacular error.”

By the way. Where has Academia been on all the regulatory distortion of the allocation of bank credit?

Could the Basel Committee learn enough from puzzles and poker so as to correct their misinformation?

Sir, I refer to Tim Harford’s “What puzzles and poker can teach us about misinformation” FT Weekend December 5.

When deciding on what’s more dangerous to banks the regulators in the Basel Committee, with “expert intuition” and great emotion shouted out the “below BB-” and, for their risk weighted bank capital requirements, assigned these a 150% risk weight, and a very smallish 20% to what’s rated AAA.

But, with what type of assets can those excessive exposures that could really be dangerous to our bank systems built-up, with assets rated below BB- or with assets rated AAA?

Never ever with assets perceived as risky, always with assets perceived as safe.

Sadly, the regulators had missed their lectures on conditional probabilities.

And their “expert intuitions” are so strong that they were not able to understand the clear message sent by the 2008 AAA rated MBS. 

What does Tim Harford think regulators could learn from puzzles and poker to correct their misinformation?

PS. Trying to understand the how come of the so loony bank regulations, by reading Daniel Kahneman’s “Thinking, Fast and Slow” 2011.

@PerKurowski

Sir FT, do you, or our dear The Undercover Economist Tim Harford, have an explanation for what is a monstrous regulatory mistake?

Sir, I refer to Tim Harford’s “The Changing Face of Economics” December 19.

As an economist, if I were to regulate or supervise banks, I would mostly be concerned with bankers not perceiving the credit risk correctly. Wouldn’t you?

That’s why I cannot understand why so many economist colleagues, when acting as bank regulators, can be so dumb so as to bet our banking systems on that bankers will be able to perceive what is safe correctly. 

Let me explain it having bankers answering the four possible outcomes.

If the ex ante risky, ex post turns out safe = “Great News we helped an entrepreneur to have success”

If the ex ante risky, ex post turns out safe = “You see, that is why we lend them little and charge them high risk adjusted interest rates.”

If the ex ante safe, ex post turns out safe = “Just as we expected”

If the ex ante safe, ex post turns out risky = “Holy moly what do we now do? We lend it way too much at way too low interest rates”

But the regulators in the Basel Committee, in their Basel II of 2004, assigned risk weights of only 20% for what is so dangerous to our bank systems as what human fallible credit rating agencies have rated AAA, and a whopping 150% for what has been made so innocous, by being rated below BB-?

Sir, so do you, or our dear The Undercover Economist Tim Harford, have an explanation for what is clearly a monstrous regulatory mistake? 

Or is it that you, and our dear The Undercover Economist Tim Harford, out of sheer collegiality solidarity, both agree with such dumb regulations?

If so, let me assure you that when I studied economics, it was to learn and understand economics, not to join an economists’ union/mutual admiration club.

http://perkurowski.blogspot.com/2016/04/here-are-17-reasons-for-why-i-believe.html

PS Tweet: I can understand a child believing that what’s rated below BB- is more dangerous to our bank systems than what’s rated AAA, and therefore assigning a bank capital requirement of 12% to the BB- rated assets, and only 1.6% to those rated AAA. But mature professionals?

@PerKurowski

Current bank regulations are evidence free rather than evidence based

Tim Harford suggests, “Pick a topic that matters to you”, “How to survive an election with your sanity intact” November 16.

Ok. Bank regulations. And Harford argues, “Politics… is now evidence-free rather than evidence-based”. Indeed but so are current bank regulations. 

What has caused all big bank crises was something ex ante perceived very safe that ex post turned out very risky… in other words incorrect risk assessments.

But instead of basing the capital requirements based on this empirical evidence, regulators concocted risk-weighted capital requirements based on credit risks being correctly perceived. And so they assigned a meager 20% risk-weight to dangerous AAA rated, and 150% to the so innocous below BB- rated. 

If I were a regulator I would consider my role to guard against the possibility that bankers could perceive risks incorrectly, instead of, like the Basel Committee has done, betting our bank systems on bankers always being correct. Sir, wouldn’t you too?

Harford suggests, “When someone expresses an opinion, whether you agree or disagree, ask them to elaborate. Be curious.”

Unfortunately, when thousand of times I’ve asked the question “Why do you believe that what’s perceived as risky by bankers is more dangerous to our bank systems than what they perceive as safe?” that has not generated much curiosity. What it has generated is a lot of defensive circling of the wagons. “There again goes Kurowski with his obsession”

Harford also reminds us of Alberto Brandolini’s “bullshit asymmetry” principle, “The amount of energy needed to refute bullshit is an order of magnitude bigger than to produce it.” With soon 3.000 letters to FT on the topic of “subprime banking regulations”, I can sure attest to that being true.

https://teawithft.blogspot.com/search/label/subprime%20banking%20regulations

@PerKurowski

In banking, the worst worse case scenario by far, is something perceived as very safe turning out to be very risky

Sir, Tim Harford writes “We don’t think about worst-case scenarios in the right way.” “To help us think sensibly about it, Gary Klein has argued for conducting ‘pre-mortems’ — or hypothetical postmortems. Before embarking on a project, imagine receiving a message from the future: the project failed, and spectacularly. Now ask yourself: why? Risks and snares will quickly suggest themselves — often risks that can be anticipated and prevented.” “We need to be better at predicting bad outcomes” September 21.

Indeed and what would that pre-mortem suggest as the worst-case scenario for banks regulated by means of risk weighted bank capital requirements?

1. That what was perceived as risky turned out to be risky? No bankers already knew it was risky and, if they anyhow took a chance on it, that would be with a small exposure and a high risk-adjusted interest rate.

2. That what was perceived as risky turned out to be safe? Of course not! What great news, perhaps the bank had helped a successful entrepreneur.

3. That what was perceived as safe turned out to be safe? Of course not!

4. That what was perceived as safe turned out to be risky? Holy Moly! Like those AAA rated securities.

So since that “hypothetical postmortem” was not done, the risk weighted bank capital requirements, besides seriously distorting the allocation of credit to the real economy, also produce especially large exposures to what’s perceived or decreed as especially safe, and is held against especially little capital, risking thereby especially big crises… Good job regulators!

My 2019 letter to the Financial Stability Board

@PerKurowski

What a pity Martin Weitzman did not chair the Basel Committee for Banking Supervision. If he had we would surely not have suffered the 2008 crisis.

Sir, Tim Harford when referring to an economic paper by Martin Weitzman on climate change classifies it as a “this changes everything” paper, leading him to conclude “extreme scenarios matter. What we don’t know about climate change is more important, and more dangerous, than what we do”, “How this economist rocked my world” September 14.

So I must ask why is it possible to understand that and yet so hard to understand the mistakes of bank regulations based on that what’s perceived as risky being much more dangerous to our bank systems, than what might be lurking behind that which is perceived as safe?

“The truly eye-opening contribution” — for Tim Harford — “was Weitzman’s explanation that the worst-case scenarios should rightly loom large in rational calculations.”

In January 2003 you published a letter in which I said, “Everyone knows that, sooner or later, the ratings issued by the credit agencies are just a new breed of systemic error to be propagated at modern speeds. Friends, please consider that the world is tough enough as it is”. 

Sir was it not clear I was warning about big crises resulting from some human fallible credit rating agencies assigning a very safe rating to something very risky? Like that in 2008 caused by the AAA to AA rated securities backed with mortgages to the subprime sector? European banks and US investment banks, loaded up with because with those credit ratings they were allowed according to Basel II, to leverage their capital a mind-blowing 62.5 times.

Ten years later, when it comes to bank regulations, Martin Weitzman’s wisdom about “worst case scenarios”, is still blithely ignored.

PS. In April 2003, as an Executive Director of the World Bank, in a formal statement I wrote "Nowadays, when information is just too voluminous and fast to handle, market or authorities have decided to delegate the evaluation of it into the hands of much fewer players such as the credit rating agencies. This will, almost by definition, introduce systemic risks in the market"

PS. My 2019 letter to the Financial Stability Board

PS. My 2019 letter to the IMF

@PerKurowski

To explain the 2008 financial crisis a two pieces puzzle could suffice.

Sir, Tim Harford writes, “Raghuram Rajan, when he was chief economist of the IMF, came closest to predicting the 2008 financial crisis. He later observed that economists had written insightfully on all the key issues but had lacked someone capable of putting all the pieces together”, “How economics can raise its game” June 29.

According to 2004’s Basel II, a corporate rated AAA to AA, could offer banks to leverage their equity 62.5 times (100%/(8%*20%)) with its risk adjusted interest rate, while one rated BB+ to BB-, or not rated at all, could only offer banks to have their risk adjusted interest rate leveraged 12.5 times (100%/(8%*100%))

Sir, I am not arguing whether it is better to be a hard or a soft economist but, any economist looking at that proposition and not seeing it would cause serious misallocation of bank credit, should either go back to school, perhaps to take some classes on conditional probabilities, or go out on Main-street, and learn a bit of what real life is about.

62.5 times leverage? What banker could dare resists that temptation and stay out of competition thinking, what if that AAA to AA rating is true?

PS. That leverage applied for European banks and US investment banks supervised by SEC.

@PerKurowski

The risk weighted bank capital requirements, is just a lean and mean “regression to the mean” machine.

Sir, Tim Harford when discussing luck and reversal of fortunes, holds that genius followed by mediocrity [is] likely a “regression to the mean”, or in simple terms, a return to business as usual. “It can be hard to discern luck from judgment” May 25.

Indeed, but sometimes that reversal to the mean, has nothing to do with such mystical issues as luck, but is a direct consequence of a distortion. 

As I have often written to FT about, allowing banks regulatory privileges when financing what’s perceived as safe, like sovereigns or houses, will result in too much financing of the safe, which will cause “the safe”, sooner or later to revert to become very risky.

In the same vein, those who without correcting for a crisis are now considered triumphant, like ECB’s Mario Draghi, only because they’ve managed to kick a crisis-can forward, will one day be held much accountable, when that crisis can rolls back on some, as it sure must.

@PerKurowski

When experts on different aspects collaborate they should be able to disagree, not just join a mutual admiration club.

Sir, Tim Harford writes about “a flawed statistical study by Winston Churchill’s scientific adviser Frederick Lindemann that no one had both the technical skill and the political clout to challenge. [It caused] the allied bombing of dense urban areas in Germany during the war, which not only took a terrible toll on civilians but failed in military terms by sparing industrial targets.” “Real change requires experts to collaborate” May 4.

There is a document prepared by the Basel Committee on Banking Supervision dated July 2005 and titled “An Explanatory Note on the Basel II IRB Risk Weight Functions". It can be found on the web site of the Bank for International Settlements.

It is supposed to explain the standardized risk weighted capital requirements for banks decided upon in the Basel II agreements. It does nothing of that sort, mostly because those risk weights are impossible to justify.

For instance assets rated AAA to AA rated, which ex ante perceived safety could cause banks to build up excessive exposures that could be dangerous to the bank system if these turned out ex post risky are assigned a 20% risk weight while; for assets rated a below BB- and that because of their perceived riskiness banks will not voluntarily build up excessive exposures to, and therefore represent no risk to the bank system, even if they turn out even riskier than expected, have been assigned a whopping 150% risk weight.

But that explanation was never challenged. The fact that AAA to AA rated assets could be leveraged 62.5 times by the banks, when compared to the 12.5 times allowed leverage with unsecured loans to unrated entrepreneurs, created the incentive structure for the 2008 crisis, caused by the excessive exposures to the AAA rated securities backed with mortgages to the subprime sector in the US, which turned out very risky; or by the excessive exposures to assets covered by default guarantee sold by AAA rated AIG.

Even after that crisis, the silence on it has persisted. As is our bank systems are doomed to especially large crisis, caused by especially large exposures to assets perceived ex ante as especially safe, but against which when these turn out ex post to be especially risky banks hold especially little capital.

How did the weavers in Basel manage to convince the world that with their regulations the bank systems were fully dressed, and that anyone not seeing that were unfit for their positions, stupid, or incompetent? I have, like the child in Hans Christian Andersen’s “The Emperor’s New Clothes”, shouted out innumerable times that our bank systems are now even worse of than if naked, but this has obviously not sufficed.

Harford opines “good policymaking is now a team effort. It requires different perspectives and a range of specialist expertise. We all must learn to work with people who see the world very differently”

Indeed, and there is of course more than enough “technical skill and the political clout to challenge” these regulations, but yet nothing happens. Could there perhaps be too many disincentives to do so? For instance like then not being invited to Davos? 

Sir, one day historians will scratch their heads trying to figure out the reasons for the world’s now more that thirty years silence, on the outright loony (and statist) risk weighted bank capital requirements. Do you not wonder what they in that respect could say about FT’s?

@PerKurowski

Yes we sure need a carbon tax, but its revenues, should be shared out equally to all

Sir, Tim Harford writes: “The exciting thing about the Green New Deal is that it has serious political momentum focused at addressing climate change.” “Why the world urgently needs a carbon tax” April 13.

No! That “Green New Deal” “vague, and [with] grand aims [to] win… support than [with] hard practicalities”, far from being exciting is scary. As Harford thinks, “climate change is far too important a challenge to entrust to oil companies” I am sure that “climate change is far too important a challenge” to entrust its spending decisions of the fight against it, to some few who might be pursuing a different objective.

As I’ve said over and over again, the more you are concerned about climate change, the more you should be concerned with keeping the climate-change-fight profiteers as far away as possible.

Harford writes: “A lump-sum subsidy can encourage the uptake of electric cars — but a carbon tax will also reward those who cycle instead of driving.” Sir, I just ask, would the rewards for cycling not become so much real, if all carbon tax revenues were shared out equally to all?

PS. Harford mentions “a carbon permit auction” as a “close sibling” to a carbon tax. Not so. A carbon permit auction is nothing but a new type of those indulgences that were sold by the Catholic Church in order to permit sinning. It is a twist of history to see that Martin Luther’s Protestant Germany is one that now most supports such indulgences.

@PerKurowski

If only regulators had analyzed their risk weighted capital requirements for banks in terms of bets.

Sir, Tim Harford refers to Nassim Taleb, warning of “the ‘ludic fallacy’ — treating the unknown risks of life as though they were the known risks of a game of chance”, “Experimental living beats thinking in bets” February 17.

That is somewhat like when regulators treated the unknown risks in banking and set their risk weighted capital requirements. 

Harford also mentions Annie Duke’s recommendation “that we should always be willing to ask ourselves, ‘do I want to bet on that’ — it’s easy to be overconfident if there are no obvious consequences for being wrong. A bet forces us to think about the odds and the possibility that someone else may know better.”

Oh, if only our bank regulators have asked themselves: “Do we want to bet our bank systems on that what gets an AAA to AA rating, issued by human fallible credit rating agencies, is so safe we should only need to require banks to hold 1.6% in capital against such assets and so allow them to leverage 62.5 times with these?” Had they posed that question, the crisis resulting from excessive exposures to AAA rated securities backed with mortgages to the subprime sector would not have happened.

“We have risk-weighted the capital requirements for banks in order to make our bank system safer.” Someone has either played tricks on them or they are bluffing. The sad part is that so few dare to call them out on it. And, when I do that, many just brush me off with a “he’s just got an obsession”.

Though Harford accepts that “Thinking in bets is a rigorous and admirable habit” for many cases he favors “Thinking in experiments [as that] allows us to learn [and might be] less painful.

In case of bank regulations experiments are not needed. Just go out and look at all the crises and try to find one that was caused by excessive exposures to something perceived as risky when placed on the balance sheets of banks. None! Should that not tell you something about our unwillingness to learn when the lessons are hard to swallow? 

Sir, using Edward Thorp’s real casino risks, in banking, the Basel Committee represents “the crooked dealer” and the risk weighted capital requirements “the poisoned coffee” 

Casino games, like roulette, are all based on offering all possible bets exactly the same expected payout adjusted for their respective probabilities. If it was not so, no casino would survive. So it was in banking, until risk weighted capital requirements offered banks higher risk adjusted return on equity for what was perceived, decreed or concocted as safe (betting on a color), than for what was perceived as risky (betting on a single number). The consequence? Our bank systems will fail especially bad, by building up especially large exposures to what is especially perceived as safe, against especially little capital. The 2008 crisis, and Greece, were just canaries in that mine.

PS. Here is the current summary of why I know the risk weighted capital requirements for banks, is utter and dangerous nonsense.

@PerKurowski

Redistribution profiteers have a vested interest in us ignoring the wealthy already redistribute their purchase capacity.

Sir, Tim Harford writes “One academic paper produced by Emmanuel Saez (a star in the study of inequality) and Peter Diamond (a Nobel laureate and colleague of Mirrlees) estimated that the combined rate of tax on the income of high earners could be 73 per cent in the US without proving counter-productive…[for that they] assume that a dollar is 25 times more valuable to a person on about $50,000 a year than to a person on $500,000.” “The super-rich are an easy target for tax rises” February 2.

Indeed, and that‘s why those with much higher income sometimes buy shoes that are 25 times more expensive than those earning much less. But, where does that type of analysis take us? Should jobs producing expensive manually produced shoes be prohibited? Should we have dollars with sensors that measure the value we assign to them? 

The problem with all the “resolve poverty and inequality by taxing the wealthy” is that it ignores the fact that all the purchase power that the income of the wealthy contains, is immediately returned to the real economy when purchasing assets and services. 

In this sense those prescribing higher taxes on wealth are, at the end of the day just arguing, they are better redistributors than the wealthy. Are they? Perhaps yes, perhaps no. In Venezuela those redistributing wealth have clearly done so in order to get their hands on the wealth. In Venezuela we have a saying that goes “The one who cuts the cake in order to distribute the cake, keeps the best part of the cake.

PS. Thomas Piketty should visit the Museum of Louvre in his Paris, and make a checklist of how much would not have existed there, had it not been for some “filthy rich”

@PerKurowski

The Blue Monday fiction is nothing when compared to Basel Committee’s risk weighted capital requirements fiction.

Sir, Tim Harford writes, “Given that it is pure fiction, the “Blue Monday” meme is showing surprising longevity”, and he asks “Why do such ideas endure? What do they tell us about our attitude to science, evidence or the truth itself?” “The pseudoscience of Blue Monday hits trust” January 26.

But really, what’s the significance of some falling for an innocous Blue Monday fiction, when compared to that fiction that what's perceived as risky is more dangerous to our bank systems than what's perceived as safe? 

The first one might cause some to travel on not a really adequate date for them, the latter, when translated into risk weighted bank capital requirements for banks, distorts the allocation of credit to the real economy; only guaranteeing especially large crises, because of especially large bank exposures to something perceived as especially safe that turns out to be especially risky, held against especially little bank capital.

Harford refers to Onora O’Neill in that “we should be aiming for a better ability to trust what is trustworthy and to mistrust what is not”. In the case of journalists he says that “the non-experts among us could do more to keep ourselves well-informed.”

Since the information on bank regulations is out there readily available for anyone who cares to look at it, that should suffice to answer his question on whether “we should be more trusting, or more sceptical?”

Sir, Skepticism 101 courses are much needed. May I humbly suggest you and Harford could benefit from taking one of these?

@PerKurowski

Imposing a marginal minuscule cost per web-ad-message could perhaps help level the playing field for the boring truths against the much more fun fake news.

Sir, Tim Harford expresses it clearly when he writes, “Fake news itself does not pose an existential threat either to democracy or the free press. What does pose such a threat is a draconian response from governments.” “There is no need to panic about fake news” January 5.

Indeed but Basic Skepticism 101 courses are still much needed. I have for decades objected to that draconian response from regulators that states: “We will make your banks safer with risk weighted capital requirements”, which they based on the loony idea that what’s perceived as risky is more dangerous to our bank systems than what is perceived as safe. 

Of course that is as fake as a regulation can be. Not only does it distort the allocation of credit to the real economy but it also puts bank crises on steroids. As for now, that only guarantees especially large crisis, because of especially large exposures, to what is especially perceived as safe, against especially little capital.

Hartford also worries about “that there is far too little transparency over political advertising in the digital age: we don’t know who is paying for what message to be shown to whom”. I agree but one important cause for that is that there is no marginal cost to be paid by those spreading news and ads on the web.

If every ad messaging on the web forced the messenger to pay a minuscule amount per message, then we would be more carefully targeted, meaning wasting less of our limited attention span, and it would be less easy for fake-more-fun-news messengers to compete with “real” not-as-fun-news outfits, if there now is such a thing.

PS. If those revenues help fund an unconditional universal basic income, then it would be even better. 

@PerKurowski

Even the best central bankers can mess it up, royally

Sir, Tim Harford writes: “A flint-hearted technocrat can at times deliver better results for everyone. In the early 1980s, Fed chair Paul Volcker demonstrated the basic idea that inflation could be crushed by a sufficiently badass central banker.” “Stop sniping at central banks and set clear targets” December 16.

Indeed, and Paul Volcker was a hero of mine too, that is until I realized his role as the facilitator of the risk weighted capital requirements for banks.

In his book “Keeping at it”, penned together with Christine Harper, Paul Volcker writes: “The Europeans, as a group, firmly insisted upon a “risk-based” approach, seemingly more sophisticated because it calculated assets based on how risky they seemed to be. They felt it was common sense that certain kind of assets –certainly including domestic government bonds but also home mortgages and other sovereign debt- shouldn’t require much if any capital. Commercial loans, by contrast, would have strict and high capital requirements, whatever the credit rating might be…. At the end of a European tour in September in 1986, at an informal dinner with the Bank of England’s then governor Robin Leigh-Pemberton… without a lot of forethought, I suggested to him that if it was necessary to reach agreement, I’d try to sell the risk-based approach to my US colleagues.”

And that was that! In that moment, accepting the European nonsense that what bankers perceive as risky is more dangerous to our bank systems than what banker perceive as safe, Paul Volcker, a central banker, helped condemn us to suffer especially severe bank crisis, resulting from especially large exposures, to what was especially perceived as safe, against especially little capital. I thank him not!

Harford opines “The health of our democracies demands that our politicians start taking responsibility again”

Absolutely! And with respect to bank regulations that requires the politicians to ask for explanations like: Why do you risk weigh the assets based on their perceived risk and not on their risk based on how bankers perceive their risk? Have you never heard about conditional probabilities?

PS. The Basel Committee document that provides an explanation on the portfolio invariant risk weighted capital requirements does not make any sense to me, but perhaps Tim Harford understands it. If so could you please ask him to explain it to us? 

@PerKurowski

What could “megaprojects” have taught us about the EU and the euro?

Sir, Tim Harford, with the help of Bent Flyvbjerg, “perhaps the world’s leading authority on ‘megaprojects’”, analyzes Brexit “What megaprojects can teach us about Brexit” October 26.

It is a useful exercise though I keep on being surprised by how little attention is given to other closely related megaprojects such as that of the European Union and the euro. 

A complete Brexit project should analyze the costs for Britain of EU not solving the much-ignored challenges the euro poses to EU, as these could be huge. Anyone proposing a Remain, should at least try to get a clear answer from EU on what it intends to do to make absolutely certain the euro will not bring EU down, or if that happens that at least non-euro members are not called to share in its costs.

I have no idea if the EU/euro project was “prepared thoroughly”, without “well-known cognitive biases”, or if it was carried out by “an experienced team”.

But when it comes to “try to break a large project into smaller, standalone chunks, so that the failure of one is not a failure of everything” clearly that’s not the case here, since the failure of the euro could quite likely bring the EU down.

The “everyone having an incentive to make things move smoothly” is doubtful too. Surplus countries find it easier to live with a euro weakened by deficit countries, though that does not work the other way round.

With respect to having an early warning system, so problems can be spotted and fixed before they grow, I seriously doubt it exists. Especially since EU authorities seriously compounded any euro challenges with statist “Sovereign Debt Privileges”, that which assigns a 0%capital requirements for banks when holding eurozone’ sovereign debts denominated in euros... a currency that in most generous terms could qualify as quasi domestic.

The challenges for EU of the euro must have been well known.

@PerKurowski

What’s the safest way to fight climate change: by centralized planning or through the market?

Sir, Tim Harford writes: We should do more to encourage innovation that attacks the climate change problem… The most obvious first step (among several worth trying) is a stiff tax on carbon dioxide emissions” “Let’s innovate a way out of our climate crisis” October 13.

I agree 100% with that. The real question though is what is to be done with the revenues of such stiff tax? There are different options. 

The first to allow governments to manage these, setting it up for good results, but also a quite likely having it much captured by the war-on-climate-change profiteers. 

The second to share out these revenues equally among all citizens, like by helping to fund a Universal Basic Income, and so that it is the market that will take the decisions on what’s to be done.

Of course there are also pseudo market solutions, like those carbon emission permits trading that handed over to speculators, a market in non-transparent carbon emission indulgences.

Sir, I am totally for the sharing out all those tax revenues among the citizens option. That would minimize the distortions, and align everyone’s incentives in the fights against climate change and poverty.

PS. In May 2016 you published a letter I wrote on how to fight the pollution in Mexico City, which was based on these arguments.

http://ourpiedaterre.blogspot.com

@PerKurowski